[RFC PATCH bpf-next v2 4/4] error-injection: Support fault injection framework

[Masami Hiramatsu]

Support in-kernel fault-injection framework via debugfs.
This allows you to inject a conditional error to specified
function using debugfs interfaces.

Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
---
 Documentation/fault-injection/fault-injection.txt |    5 +
 kernel/Makefile                                   |    1 
 kernel/fail_function.c                            |  169 +++++++++++++++++++++
 lib/Kconfig.debug                                 |   10 +
 4 files changed, 185 insertions(+)
 create mode 100644 kernel/fail_function.c

diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt
index 918972babcd8..6243a588dd71 100644
--- a/Documentation/fault-injection/fault-injection.txt
+++ b/Documentation/fault-injection/fault-injection.txt
@@ -30,6 +30,11 @@ o fail_mmc_request
   injects MMC data errors on devices permitted by setting
   debugfs entries under /sys/kernel/debug/mmc0/fail_mmc_request
 
+o fail_function
+
+  injects error return on specific functions by setting debugfs entries
+  under /sys/kernel/debug/fail_function. No boot option supported.
+
 Configure fault-injection capabilities behavior
 -----------------------------------------------
 
diff --git a/kernel/Makefile b/kernel/Makefile
index 172d151d429c..f85ae5dfa474 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_KCOV) += kcov.o
 obj-$(CONFIG_KPROBES) += kprobes.o
+obj-$(CONFIG_FAIL_FUNCTION) += fail_function.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
new file mode 100644
index 000000000000..203d3582487a
--- /dev/null
+++ b/kernel/fail_function.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fail_function.c: Function-based error injection
+ */
+#include <linux/error-injection.h>
+#include <linux/debugfs.h>
+#include <linux/fault-inject.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs);
+
+static DEFINE_MUTEX(fei_lock);
+static struct {
+	struct kprobe kp;
+	unsigned long retval;
+	struct fault_attr attr;
+} fei_attr = {
+	.kp = { .pre_handler = fei_kprobe_handler, },
+	.retval = ~0UL,	/* This indicates -1 in long/int return value */
+	.attr = FAULT_ATTR_INITIALIZER,
+};
+
+static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
+{
+	if (should_fail(&fei_attr.attr, 1)) {
+		regs_set_return_value(regs, fei_attr.retval);
+		override_function_with_return(regs);
+		/* Kprobe specific fixup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
+		return 1;
+	}
+
+	return 0;
+}
+NOKPROBE_SYMBOL(fei_kprobe_handler)
+
+static void *fei_seq_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&fei_lock);
+	return *pos == 0 ? (void *)1 : NULL;
+}
+
+static void fei_seq_stop(struct seq_file *m, void *v)
+{
+	mutex_unlock(&fei_lock);
+}
+
+static void *fei_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return NULL;
+}
+
+static int fei_seq_show(struct seq_file *m, void *v)
+{
+	if (fei_attr.kp.addr)
+		seq_printf(m, "%pf\n", fei_attr.kp.addr);
+	else
+		seq_puts(m, "# not specified\n");
+	return 0;
+}
+
+static const struct seq_operations fei_seq_ops = {
+	.start	= fei_seq_start,
+	.next	= fei_seq_next,
+	.stop	= fei_seq_stop,
+	.show	= fei_seq_show,
+};
+
+static int fei_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fei_seq_ops);
+}
+
+static ssize_t fei_write(struct file *file, const char __user *buffer,
+			 size_t count, loff_t *ppos)
+{
+	unsigned long addr;
+	char *buf, *sym;
+	int ret;
+
+	/* cut off if it is too long */
+	if (count > KSYM_NAME_LEN)
+		count = KSYM_NAME_LEN;
+	buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, buffer, count)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	buf[count] = '\0';
+	sym = strstrip(buf);
+
+	if (strlen(sym) == 0 || sym[0] == '0') {
+		if (fei_attr.kp.addr) {
+			unregister_kprobe(&fei_attr.kp);
+			fei_attr.kp.addr = NULL;
+		}
+		ret = count;
+		goto out;
+	}
+
+	addr = kallsyms_lookup_name(sym);
+	if (!addr) {
+		ret = -EINVAL;
+		goto out;
+	}
+	if (!within_error_injection_list(addr)) {
+		ret = -ERANGE;
+		goto out;
+	}
+
+	if (fei_attr.kp.addr) {
+		unregister_kprobe(&fei_attr.kp);
+		fei_attr.kp.addr = NULL;
+	}
+	fei_attr.kp.addr = (void *)addr;
+	ret = register_kprobe(&fei_attr.kp);
+	if (ret < 0)
+		fei_attr.kp.addr = NULL;
+	else
+		ret = count;
+out:
+	kfree(buf);
+	return ret;
+}
+
+static const struct file_operations fei_ops = {
+	.open =		fei_open,
+	.read =		seq_read,
+	.write =	fei_write,
+	.llseek =	seq_lseek,
+	.release =	seq_release,
+};
+
+static int __init fei_debugfs_init(void)
+{
+	struct dentry *dir;
+
+	dir = fault_create_debugfs_attr("fail_function", NULL,
+					&fei_attr.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	// injectable attribute is just a symlink of error_inject/list
+	if (!debugfs_create_symlink("injectable", dir,
+				    "../error_injection/list"))
+		goto error;
+
+	if (!debugfs_create_file("inject", 0600, dir, NULL, &fei_ops))
+		goto error;
+
+	if (!debugfs_create_ulong("retval", 0600, dir, &fei_attr.retval))
+		goto error;
+
+	return 0;
+error:
+	debugfs_remove_recursive(dir);
+	return -ENOMEM;
+}
+
+late_initcall(fei_debugfs_init);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index fe88ac0f003c..15c6609a1bb8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1551,6 +1551,16 @@ config FAIL_FUTEX
 	help
 	  Provide fault-injection capability for futexes.
 
+config FAIL_FUNCTION
+	bool "Fault-injection capability for functions"
+	depends on FAULT_INJECTION_DEBUG_FS && FUNCTION_ERROR_INJECTION
+	help
+	  Provide function-based fault-injection capability.
+	  This will allow you to override a specific function with a return
+	  with given return value. As a result, function caller will see
+	  an error value and have to handle it. This is useful to test the
+	  error handling in various subsystems.
+
 config FAULT_INJECTION_DEBUG_FS
 	bool "Debugfs entries for fault-injection capabilities"
 	depends on FAULT_INJECTION && SYSFS && DEBUG_FS